Skip to main content
SpringerLink
Log in

A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle

  • Diagnostic Neuroradiology
  • Published:
Neuroradiology Aims and scope Submit manuscript

Abstract

Purpose

Deep learning-based reconstruction (DLR) has been developed to reduce image noise and increase the signal-to-noise ratio (SNR). We aimed to evaluate the efficacy of DLR for high spatial resolution (HR)-MR cisternography.

Methods

This retrospective study included 35 patients who underwent HR-MR cisternography. The images were reconstructed with or without DLR. The SNRs of the CSF and pons, contrast of the CSF and pons, and sharpness of the normal-side trigeminal nerve using full width at half maximum (FWHM) were compared between the two image types. Noise quality, sharpness, artifacts, and overall image quality of these two types of images were qualitatively scored.

Results

The SNRs of the CSF and pons were significantly higher with DLR than without DLR (CSF 21.81 ± 7.60 vs. 15.33 ± 4.03, p < 0.001; pons 5.96 ± 1.38 vs. 3.99 ± 0.48, p < 0.001). There were no significant differences in the contrast of the CSF and pons (p = 0.225) and sharpness of the normal-side trigeminal nerve using FWHM (p = 0.185) without and with DLR, respectively. Noise quality and the overall image quality were significantly higher with DLR than without DLR (noise quality 3.95 ± 0.19 vs. 2.53 ± 0.44, p < 0.001; overall image quality 3.97 ± 0.17 vs. 2.97 ± 0.12, p < 0.001). There were no significant differences in sharpness (p = 0.371) and artifacts (p = 1) without and with DLR.

Conclusion

DLR can improve the image quality of HR-MR cisternography by reducing image noise without sacrificing contrast or sharpness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Abbreviations

3D:

Three-dimensional

DCT:

Discrete cosine transform

DLR:

Deep learning-based reconstruction

FASE:

Fast asymmetric spin-echo

FWHM:

Full width at half maximum

HR:

High-spatial resolution

SNR:

Signal-to-noise ratio

T1WI:

T1-weighted image

T2WI:

T2-weighted image

CNR:

Contrast-to-noise ratio

References

  1. Naganawa S, Koshikawa T, Fukatsu H, Ishigaki T, Fukuta T (2001) MR cisternography of the cerebellopontine angle: comparison of three-dimensional fast asymmetrical spin-echo and three-dimensional constructive interference in the steady-state sequences. AJNR Am J Neuroradiol 22:1179–1185

    CAS  PubMed  Google Scholar 

  2. Liu P, Saida Y, Yoshioka H, Itai Y (2003) MR imaging of epidermoids at the cerebellopontine angle. Magn Reson Med Sci 2:109–115

    Article  Google Scholar 

  3. Masuda Y, Yamamoto T, Akutsu H, Shiigai M, Masumoto T, Ishikawa E, Matsuda M, Matsumura A (2015) Usefulness of subtraction of 3D T2WI-DRIVE from contrast-enhanced 3D T1WI: preoperative evaluations of the neurovascular anatomy of patients with neurovascular compression syndrome. AJNR Am J Neuroradiol 36:317–322

    Article  CAS  Google Scholar 

  4. Nowe V, De Ridder D, Van de Heyning PH, Wang XL, Gielen J, Van Goethem J, Ozsarlak O, De Schepper AM, Parizel PM (2004) Does the location of a vascular loop in the cerebellopontine angle explain pulsatile and non-pulsatile tinnitus? Eur Radiol 14:2282–2289

    Article  CAS  Google Scholar 

  5. Ryu H, Tanaka T, Yamamoto S, Uemura K, Takehara Y, Isoda H (1999) Magnetic resonance cisternography used to determine precise topography of the facial nerve and three components of the eighth cranial nerve in the internal auditory canal and cerebellopontine cistern. J Neurosurg 90:624–634

    Article  CAS  Google Scholar 

  6. Hentschel MA, Kunst HPM, Rovers MM, Steens SCA (2018) Diagnostic accuracy of high-resolution T2-weighted MRI vs contrast-enhanced T1-weighted MRI to screen for cerebellopontine angle lesions in symptomatic patients. Clin Otolaryngol 43:805–811

    Article  CAS  Google Scholar 

  7. Gamaleldin OA, Donia MM, Elsebaie NA, Abdelkhalek Abdelrazek A, Rayan T, Khalifa MH (2020) Role of fused three-dimensional time-of-flight magnetic resonance angiography and 3-dimensional T2-weighted imaging sequences in neurovascular compression. World Neurosurg 133:e180–e186

    Article  Google Scholar 

  8. Kanoto M, Toyoguchi Y, Hosoya T, Oda A, Sugai Y (2013) Visualization of the trochlear nerve in the cistern with use of high-resolution turbo spin-echo multisection motion-sensitized driven equilibrium. AJNR Am J Neuroradiol 34:1434–1437

    Article  CAS  Google Scholar 

  9. Aja-Fernandez S, Vegas-Sanchez-Ferrero G, Tristan-Vega A (2014) Noise estimation in parallel MRI: GRAPPA and SENSE. Magn Reson Imaging 32:281–290

    Article  Google Scholar 

  10. Pruessmann KP, Weiger M, Scheidegger MB, Boesiger P (1999) SENSE: sensitivity encoding for fast MRI. Magn Reson Med 42:952–962

    Article  CAS  Google Scholar 

  11. Monch S, Sollmann N, Hock A, Zimmer C, Kirschke JS, Hedderich DM (2019) Magnetic resonance imaging of the brain using compressed sensing - quality assessment in daily clinical routine. Clin Neuroradiol 30:279–286. https://doi.org/10.1007/s00062-019-00789-x

    Article  PubMed  Google Scholar 

  12. Zhang T, Chowdhury S, Lustig M, Barth RA, Alley MT, Grafendorfer T, Calderon PD, Robb FJ, Pauly JM, Vasanawala SS (2014) Clinical performance of contrast enhanced abdominal pediatric MRI with fast combined parallel imaging compressed sensing reconstruction. J Magn Reson Imaging 40:13–25

    Article  CAS  Google Scholar 

  13. Sharma SD, Fong CL, Tzung BS, Law M, Nayak KS (2013) Clinical image quality assessment of accelerated magnetic resonance neuroimaging using compressed sensing. Investig Radiol 48:638–645

    Article  Google Scholar 

  14. Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, Mahajan V, Rao P, Warier P (2018) Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet 392:2388–2396

    Article  Google Scholar 

  15. Ueda D, Yamamoto A, Nishimori M, Shimono T, Doishita S, Shimazaki A, Katayama Y, Fukumoto S, Choppin A, Shimahara Y, Miki Y (2019) Deep learning for MR angiography: automated detection of cerebral aneurysms. Radiology 290:187–194

    Article  Google Scholar 

  16. Perkuhn M, Stavrinou P, Thiele F, Shakirin G, Mohan M, Garmpis D, Kabbasch C, Borggrefe J (2018) Clinical evaluation of a multiparametric deep learning model for glioblastoma segmentation using heterogeneous magnetic resonance imaging data from clinical routine. Investig Radiol 53:647–654

    Article  Google Scholar 

  17. Lin L, Dou Q, Jin YM, Zhou GQ, Tang YQ, Chen WL, Su BA, Liu F, Tao CJ, Jiang N, Li JY, Tang LL, Xie CM, Huang SM, Ma J, Heng PA, Wee JTS, Chua MLK, Chen H, Sun Y (2019) Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma. Radiology 291:677–686

    Article  Google Scholar 

  18. Dunnmon JA, Yi D, Langlotz CP, Ré C, Rubin DL, Lungren MP (2019) Assessment of convolutional neural networks for automated classification of chest radiographs. Radiology 290:537–544

    Article  Google Scholar 

  19. Wang H, Zhang J, Bao S, Liu J, Hou F, Huang Y, Chen H, Duan S, Hao D, Liu J (2020) Preoperative MRI-based radiomic machine-learning nomogram may accurately distinguish between benign and malignant soft-tissue lesions: a two-center study. J Magn Reson Imaging. https://doi.org/10.1002/jmri.27111

  20. Jiang D, Dou W, Vosters L, Xu X, Sun Y, Tan T (2018) Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network. Jpn J Radiol 36:566–574

    Article  Google Scholar 

  21. Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26:3142–3155

    Article  Google Scholar 

  22. Kidoh M, Shinoda K, Kitajima M, Isogawa K, Nambu M, Uetani H, Morita K, Nakaura T, Tateishi M, Yamashita Y, Yamashita Y (2019) Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers. Magn Reson Med Sci 19:195–206. https://doi.org/10.2463/mrms.mp.2019-0018

    Article  PubMed  PubMed Central  Google Scholar 

  23. Isogawa K, Ida T, Shiodera T, Takeguchi T (2018) Deep shrinkage convolutional neural network for adaptive noise reduction. IEEE Signal Process Lett 25:224–228

    Article  Google Scholar 

  24. Erturk MA, Bottomley PA, El-Sharkawy AM (2013) Denoising MRI using spectral subtraction. IEEE Trans Biomed Eng 60:1556–1562

    Article  Google Scholar 

  25. Sijbers J, den Dekker AJ, Van der Linden A, Verhoye TM, Van Dyck D (1999) Adaptive anisotropic noise filtering for magnitude MR data. Magn Reson Imaging 17:1533–1539

    Article  CAS  Google Scholar 

  26. Donoho DL (1995) De-noising by soft-thresholding. IEEE Trans Inf Theory 41:613–627

    Article  Google Scholar 

  27. Laine AF (2000) Wavelets in temporal and spatial processing of biomedical images. Annu Rev Biomed Eng 2:511–550

    Article  CAS  Google Scholar 

  28. Yang X, Fei B (2011) A wavelet multiscale denoising algorithm for magnetic resonance (MR) images. Meas Sci Technol 22:25803

    Article  Google Scholar 

Download references

Funding

None.

Author information

Authors and Affiliations

  1. Department of Diagnostic Radiology, Faculty of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuo-ku, Kumamoto, Japan

    Hiroyuki Uetani, Takeshi Nakaura, Mika Kitajima, Machiko Tateishi, Akira Sasao, Seitaro Oda, Osamu Ikeda & Yasuyuki Yamashita

  2. Canon Medical Systems Corporation, MRI Sales Department, Sales Engineer Group, 70-1, Yanagi-cho, Saiwai-ku, Kawasaki-shi, Kanagawa, 212-0015, Japan

    Yuichi Yamashita

  3. Department of Diagnostic, Neurosurgery, Faculty of Life Sciences, Kumamoto University, 1-1-1 Honjo, Chuo-ku, Kumamoto, Japan

    Tadashi Hamasaki

  4. Department of Radiology, Kumamoto University Hospital, 1-1-1 Honjo, Chuo-ku, Kumamoto, Japan

    Kosuke Morita

Authors
  1. Hiroyuki Uetani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Takeshi Nakaura
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mika Kitajima
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuichi Yamashita
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tadashi Hamasaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Machiko Tateishi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Kosuke Morita
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Akira Sasao
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Seitaro Oda
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Osamu Ikeda
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yasuyuki Yamashita
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by Hiroyuki Uetani, Tadashi Hamasaki, Machiko Tateishi, Kosuke Morita, Akira Sasao, and Seitaro Oda. The first draft of the manuscript was written by Hiroyuki Uetani, and all authors commented on the previous versions of the manuscript. All authors read and approved the final manuscript.

Conceptualization: Hiroyuki Uetani and Takeshi Nakaura

Data collection: Hiroyuki Uetani, Tadashi Hamasaki, Machiko Tateishi, Kosuke Morita, Akira Sasao, and Seitaro Oda

Methodology: Hiroyuki Uetani, Takeshi Nakaura, Mika Kitajima, and Yuichi Yamashita

Formal analysis and investigation: Hiroyuki Uetani, Takeshi Nakaura, Mika Kitajima, and Machiko Tateishi

Writing—original draft preparation: Hiroyuki Uetani

Writing—review and editing: Takeshi Nakaura, Mika Kitajima, Osamu Ikeda, and Yasuyuki Yamashita

Supervision: Takeshi Nakaura, Mika Kitajima, Osamu Ikeda, and Yasuyuki Yamashita

Corresponding author

Correspondence to Hiroyuki Uetani.

Ethics declarations

Conflict of interest

Yuichi Yamashita is an employee of Canon Medical Systems. The other authors declare that they have no conflicts of interest.

Ethical approval

All procedures followed the clinical study guidelines of the ethics committee of Kumamoto university hospital (Kumamoto, Japan), and they were approved by our institutional review board.

Informed consent

For this type of study, formal consent is not required.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Uetani, H., Nakaura, T., Kitajima, M. et al. A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle. Neuroradiology 63, 63–71 (2021). https://doi.org/10.1007/s00234-020-02513-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00234-020-02513-w

Keywords

Search

Navigation